activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Universal Algorithm-Implicit Learning

Stefano Woerner, Seong Joon Oh, Christian F. Baumgartner

Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literatu…

cs.LG2026

Dynamics Reveals Structure: Challenging the Linear Propagation Assumption

Hoyeon Chang, Bálint Mucsányi, Seong Joon Oh

Neural networks adapt through first-order parameter updates, yet it remains unclear whether such updates preserve logical coherence. We investigate the geometric limits of the Line…

cs.LG2025

LLM generation novelty through the lens of semantic similarity

Philipp Davydov, Ameya Prabhu, Matthias Bethge +2

Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it against full pretraining corpora is computationally challenging. Existing evaluations ofte…

cs.LG2025

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

Alexander Rubinstein, Benjamin Raible, Martin Gubri +1

Evaluating modern machine learning models has become prohibitively expensive. Benchmarks such as LMMs-Eval and HELM demand thousands of GPU hours per model. Costly evaluation reduc…

cs.LG2024

Scalable Ensemble Diversification for OOD Generalization and Detection

Alexander Rubinstein, Luca Scimeca, Damien Teney +1

Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and…

cs.LG2024

Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents

Evgenii Kortukov, Alexander Rubinstein, Elisa Nguyen +1

Retrieval-augmented generation (RAG) mitigates many problems of fully parametric language models, such as temporal degradation, hallucinations, and lack of grounding. In RAG, the m…